Mixture-of-Experts (MoE) models scale more effectively than dense models due to sparse computation through expert routing, selectively activating only a small subset of expert modules. However, sparse computation challenges traditional training practices, as discrete expert routing hinders standard backpropagation and thus gradient-based optimization, which are the cornerstone of deep learning. To better pursue the scaling power of MoE, we introduce GRIN (GRadient-INformed MoE training), which incorporates sparse gradient estimation for expert routing and configures model parallelism to avoid token dropping. Applying GRIN to autoregressive language modeling, we develop a top-2 16$\times$3.8B MoE model. Our model, with only 6.6B activated parameters, outperforms a 7B dense model and matches the performance of a 14B dense model trained on the same data. Extensive evaluations across diverse tasks demonstrate the potential of GRIN to significantly enhance MoE efficacy, achieving 79.4 on MMLU, 83.7 on HellaSwag, 74.4 on HumanEval, and 58.9 on MATH.

This paper explores the potential application of Deep Reinforcement Learning in the furniture industry. To offer a broad product portfolio, most furniture manufacturers are organized as a job shop, which ultimately results in the Job Shop Scheduling Problem (JSSP). The JSSP is addressed with a focus on extending traditional models to better represent the complexities of real-world production environments. Existing approaches frequently fail to consider critical factors such as machine setup times or varying batch sizes. A concept for a model is proposed that provides a higher level of information detail to enhance scheduling accuracy and efficiency. The concept introduces the integration of DRL for production planning, particularly suited to batch production industries such as the furniture industry. The model extends traditional approaches to JSSPs by including job volumes, buffer management, transportation times, and machine setup times. This enables more precise forecasting and analysis of production flows and processes, accommodating the variability and complexity inherent in real-world manufacturing processes. The RL agent learns to optimize scheduling decisions. It operates within a discrete action space, making decisions based on detailed observations. A reward function guides the agent's decision-making process, thereby promoting efficient scheduling and meeting production deadlines. Two integration strategies for implementing the RL agent are discussed: episodic planning, which is suitable for low-automation environments, and continuous planning, which is ideal for highly automated plants. While episodic planning can be employed as a standalone solution, the continuous planning approach necessitates the integration of the agent with ERP and Manufacturing Execution Systems. This integration enables real-time adjustments to production schedules based on dynamic changes.

This paper proposes Hamiltonian Learning, a novel unified framework for learning with neural networks "over time", i.e., from a possibly infinite stream of data, in an online manner, without having access to future information. Existing works focus on the simplified setting in which the stream has a known finite length or is segmented into smaller sequences, leveraging well-established learning strategies from statistical machine learning. In this paper, the problem of learning over time is rethought from scratch, leveraging tools from optimal control theory, which yield a unifying view of the temporal dynamics of neural computations and learning. Hamiltonian Learning is based on differential equations that: (i) can be integrated without the need of external software solvers; (ii) generalize the well-established notion of gradient-based learning in feed-forward and recurrent networks; (iii) open to novel perspectives. The proposed framework is showcased by experimentally proving how it can recover gradient-based learning, comparing it to out-of-the box optimizers, and describing how it is flexible enough to switch from fully-local to partially/non-local computational schemes, possibly distributed over multiple devices, and BackPropagation without storing activations. Hamiltonian Learning is easy to implement and can help researches approach in a principled and innovative manner the problem of learning over time.

This paper introduces Cobweb4L, a novel approach for efficient language model learning that supports masked word prediction. The approach builds on Cobweb, an incremental system that learns a hierarchy of probabilistic concepts. Each concept stores the frequencies of words that appear in instances tagged with that concept label. The system utilizes an attribute value representation to encode words and their surrounding context into instances. Cobweb4L uses the information theoretic variant of category utility and a new performance mechanism that leverages multiple concepts to generate predictions. We demonstrate that with these extensions it significantly outperforms prior Cobweb performance mechanisms that use only a single node to generate predictions. Further, we demonstrate that Cobweb4L learns rapidly and achieves performance comparable to and even superior to Word2Vec. Next, we show that Cobweb4L and Word2Vec outperform BERT in the same task with less training data. Finally, we discuss future work to make our conclusions more robust and inclusive.

Understanding emotions is fundamental to human interaction and experience. Humans easily infer emotions from situations or facial expressions, situations from emotions, and do a variety of other affective cognition. How adept is modern AI at these inferences? We introduce an evaluation framework for testing affective cognition in foundation models. Starting from psychological theory, we generate 1,280 diverse scenarios exploring relationships between appraisals, emotions, expressions, and outcomes. We evaluate the abilities of foundation models (GPT-4, Claude-3, Gemini-1.5-Pro) and humans (N = 567) across carefully selected conditions. Our results show foundation models tend to agree with human intuitions, matching or exceeding interparticipant agreement. In some conditions, models are ``superhuman'' -- they better predict modal human judgements than the average human. All models benefit from chain-of-thought reasoning. This suggests foundation models have acquired a human-like understanding of emotions and their influence on beliefs and behavior.

The introduction of generative pre-trained models, like GPT-4, has introduced a phenomenon known as prompt engineering, whereby model users repeatedly write and revise prompts while trying to achieve a task. Using these AI models for intelligent features in software applications require using APIs that are controlled through developer-written prompts. These prompts have powered AI experiences in popular software products, potentially reaching millions of users. Despite the growing impact of prompt-powered software, little is known about its development process and its relationship to programming. In this work, we argue that some forms of prompts are programs, and that the development of prompts is a distinct phenomenon in programming. We refer to this phenomenon as prompt programming. To this end, we develop an understanding of prompt programming using Straussian grounded theory through interviews with 20 developers engaged in prompt development across a variety of contexts, models, domains, and prompt complexities. Through this study, we contribute 14 observations about prompt programming. For example, rather than building mental models of code, prompt programmers develop mental models of the FM's behavior on the prompt and its unique qualities by interacting with the model. While prior research has shown that experts have well-formed mental models, we find that prompt programmers who have developed dozens of prompts, each with many iterations, still struggle to develop reliable mental models. This contributes to a rapid and unsystematic development process. Taken together, our observations indicate that prompt programming is significantly different from traditional software development, motivating the creation of tools to support prompt programming. Our findings have implications for software engineering practitioners, educators, and researchers.

6D object pose estimation involves determining the three-dimensional translation and rotation of an object within a scene and relative to a chosen coordinate system. This problem is of particular interest for many practical applications in industrial tasks such as quality control, bin picking, and robotic manipulation, where both speed and accuracy are critical for real-world deployment. Current models, both classical and deep-learning-based, often struggle with the trade-off between accuracy and latency. Our research focuses on enhancing the speed of a prominent state-of-the-art deep learning model, GDRNPP, while keeping its high accuracy. We employ several techniques to reduce the model size and improve inference time. These techniques include using smaller and quicker backbones, pruning unnecessary parameters, and distillation to transfer knowledge from a large, high-performing model to a smaller, more efficient student model. Our findings demonstrate that the proposed configuration maintains accuracy comparable to the state-of-the-art while significantly improving inference time. This advancement could lead to more efficient and practical applications in various industrial scenarios, thereby enhancing the overall applicability of 6D Object Pose Estimation models in real-world settings.

We propose a new benchmark to measure a language model's linguistic reasoning skills without relying on pre-existing language-specific knowledge. The test covers 894 questions grouped in 160 problems across 75 (mostly) extremely low-resource languages, extracted from the International Linguistic Olympiad corpus. To attain high accuracy on this benchmark, models don't need previous knowledge of the tested language, as all the information needed to solve the linguistic puzzle is presented in the context. We find that, while all analyzed models rank below 25% accuracy, there is a significant gap between open and closed models, with the best-performing proprietary model at 24.05% and the best-performing open model at 8.84%.

Federated learning offers a paradigm to the challenge of preserving privacy in distributed machine learning. However, datasets distributed across each client in the real world are inevitably heterogeneous, and if the datasets can be globally aggregated, they tend to be long-tailed distributed, which greatly affects the performance of the model. The traditional approach to federated learning primarily addresses the heterogeneity of data among clients, yet it fails to address the phenomenon of class-wise bias in global long-tailed data. This results in the trained model focusing on the head classes while neglecting the equally important tail classes. Consequently, it is essential to develop a methodology that considers classes holistically. To address the above problems, we propose a new method FedLF, which introduces three modifications in the local training phase: adaptive logit adjustment, continuous class centred optimization, and feature decorrelation. We compare seven state-of-the-art methods with varying degrees of data heterogeneity and long-tailed distribution. Extensive experiments on benchmark datasets CIFAR-10-LT and CIFAR-100-LT demonstrate that our approach effectively mitigates the problem of model performance degradation due to data heterogeneity and long-tailed distribution.

The role of large language models (LLMs) in education is an increasing area of interest today, considering the new opportunities they offer for teaching, learning, and assessment. This cutting-edge tutorial provides an overview of the educational applications of NLP and the impact that the recent advances in LLMs have had on this field. We will discuss the key challenges and opportunities presented by LLMs, grounding them in the context of four major educational applications: reading, writing, and speaking skills, and intelligent tutoring systems (ITS). This COLING 2025 tutorial is designed for researchers and practitioners interested in the educational applications of NLP and the role LLMs have to play in this area. It is the first of its kind to address this timely topic.